Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2759 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3582. Min Range: -1.3582

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.3582. Min Range: -1.3582

Max Act: 1.0423. Min Act: -0.0000

Data Index: 468587 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1150451 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1431025 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6665. Min Act: -0.0000

Data Index: 597660 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1405101 (Python Code)

Max Activating Token Index: 653

Text #6

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6353. Min Act: -0.0000

Data Index: 730284 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5955. Min Act: -0.0000

Data Index: 172413 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6527. Min Act: -0.0000

Data Index: 454665 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5758. Min Act: -0.0000

Data Index: 126421 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6072. Min Act: -0.0000

Data Index: 87632 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5312. Min Act: -0.0000

Data Index: 237459 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.6301. Min Act: -0.0000

Data Index: 945965 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5746. Min Act: -0.0000

Data Index: 834202 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5146. Min Act: -0.0000

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1642576 (Python Code)

Max Activating Token Index: 878

Text #17

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5576. Min Act: -0.0000

Data Index: 934303 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1452943 (Python Code)

Max Activating Token Index: 878

Text #19

Max Range: 1.3582. Min Range: -1.3582

Max Act: 0.5250. Min Act: -0.0000

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 685